Emerging contaminants can disrupt the hormonal balance of fish and other aquatic organisms, causing reproductive problems, deformities, and even death.

They can also accumulate in the food chain, reaching humans through drinking water or seafood consumption. Some of these contaminants, such as antibiotics, can also contribute to the development of antimicrobial resistance, a global health crisis that could render many infections untreatable.

To address this challenge, scientists and engineers are turning to artificial intelligence (AI), a powerful technology that can analyze complex data and provide insights and solutions. AI can help predict, detect, and mitigate the environmental impacts of pharmaceuticals in several ways.

Predicting the Behavior and Fate of Emerging Contaminants
(Photo : Ivan Bandura/Unsplash)

One of the main difficulties in dealing with emerging contaminants is the lack of data and knowledge about their properties and behavior in the environment.

There are thousands of different drugs and chemicals that can potentially enter wastewater, and each one can have different effects depending on the concentration, temperature, pH, and other factors.

To overcome this challenge, researchers are using machine learning, a branch of AI that can learn from data and make predictions.

Machine learning models can process large amounts of information from various sources, such as chemical databases, laboratory experiments, and field measurements, and identify patterns and relationships that are not obvious to humans.

For example, a team of researchers from the University of Waterloo in Canada developed a machine learning approach that can predict the concentration of emerging contaminants in wastewater based on the population size, drug consumption, and wastewater treatment efficiency of a given region. This approach can help estimate the exposure and risk of these contaminants to aquatic life and humans.

Another example is a study by scientists from the University of California, Berkeley, who used a machine learning technique called self-organizing maps to cluster and classify different types of emerging contaminants based on their chemical structure and behavior.

This technique can help understand how these contaminants interact with each other and with the environment, and how they can be removed or degraded.

Also Read: Biochar Created from Agricultural Waste Adsorbs Wastewater Contaminants

Detecting and Monitoring Emerging Contaminants in Real Time

Another challenge in dealing with emerging contaminants is the lack of reliable and affordable methods to detect and monitor them in the environment. Conventional methods, such as chromatography and mass spectrometry, are expensive, time-consuming, and require specialized equipment and personnel.

AI can help overcome this challenge by providing faster, cheaper, and more accessible methods to detect and monitor emerging contaminants in real time.

AI can enhance the performance and accuracy of existing sensors and devices, or enable the development of new ones, that can measure the presence and concentration of these contaminants in water samples.

For instance, researchers from the University of Illinois at Urbana-Champaign developed a smartphone-based device that can detect trace amounts of antibiotics in water using a paper strip and a machine learning algorithm.

The device uses the color change of the paper strip, which reacts with the antibiotics, as an input for the algorithm, which then outputs the concentration of the antibiotics. The device can be operated by anyone with a smartphone and an internet connection, and can provide results in minutes.

Another example is a project by IBM Research and the University of Zurich, which aims to create a low-cost, portable, and autonomous device that can monitor the quality of water sources using AI and blockchain.

The device, called Liquid AI, uses a combination of optical and electrochemical sensors to measure various parameters of water quality, such as pH, turbidity, conductivity, and temperature.

The device also uses AI to analyze the sensor data and detect the presence and concentration of emerging contaminants, such as pharmaceuticals and pesticides.

The device can communicate with other devices and share the data on a blockchain platform, creating a decentralized and secure network of water quality monitoring.

Mitigating the Impacts and Reducing the Emissions of Emerging Contaminants

The ultimate goal of dealing with emerging contaminants is to mitigate their impacts on the environment and human health, and to reduce their emissions from the source.

AI can help achieve this goal by providing insights and solutions for improving the efficiency and effectiveness of wastewater treatment and management.

Wastewater treatment plants are the main line of defense against emerging contaminants, as they can remove or degrade most of them before they reach the aquatic environment.

However, conventional wastewater treatment processes are not designed to deal with these contaminants, and some of them can pass through or form new compounds that are more toxic or persistent.

AI can help optimize and enhance the wastewater treatment processes by providing real-time feedback and control, predicting the optimal operating conditions, and identifying the best treatment methods for different types of contaminants.

For example, researchers from the University of Michigan and the University of Texas at Austin used a machine learning model to optimize the performance of a membrane bioreactor, a wastewater treatment system that uses biological and physical processes to remove contaminants.

The model can predict the optimal operating parameters, such as temperature, pressure, and flow rate, that can maximize the removal of emerging contaminants while minimizing the fouling and energy consumption of the membrane.

Related article: Landslide Prediction: Geologists Develop New AI to Forecast Where Mudslides May Happen